Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models

Title: ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models
Authors: Seneque, Gareth; Ho, Lap-Hang; Saeedi, Nafise Erfanian; Molendijk, Jeffrey; Kuperman, Ariel; Elson, Tim
Publication Year: 2025
Collection: ArXiv.org (Cornell University Library)
Subject Terms: Machine Learning; Artificial Intelligence; Computation and Language; 68T50; I.2.7
Description: We present Entropic Mutual-Information Geometry Large-Language Model Alignment (ENIGMA), a novel approach to Large-Language Model (LLM) training that jointly improves reasoning, alignment and robustness by treating an organisation's policies/principles as directions to move on a model's information manifold. Our single-loop trainer combines Group-Relative Policy Optimisation (GRPO), an on-policy, critic-free RL method with Chain-of-Thought (CoT)-format only rewards; a Self-Supervised Alignment with Mutual Information (SAMI)-style symmetric InfoNCE auxiliary; and an entropic Sinkhorn optimal-transport regulariser on hidden-state distributions to bound geometry drift. We also introduce infoNCE metrics that specialise to a standard MI lower bound under matched negatives to measure how strongly a model's CoT encodes these policies. These metrics include a Sufficiency Index (SI) that enables the selection and creation of principles that maximise downstream performance prior to training. In our experiments using small (1B) LLMs, high-SI principles predict steadier training dynamics and improved benchmark performance over GRPO ablations. Our information-geometry analysis of trained models validates desirable structural change in the manifold. These results support our hypothesis that reasoning, alignment, and robustness are projections of a single information-geometric objective, and that models trained using ENIGMA demonstrate principled reasoning without the use of a reward model, offering a path to trusted capability ; 52 pages, 10 figures, author typo corrected, abstract typo corrected
Document Type: text
Language: unknown
Relation: http://arxiv.org/abs/2510.11278
Availability: http://arxiv.org/abs/2510.11278
Accession Number: edsbas.96BBCC65
Database: BASE